Why Domain Matters: A Preliminary Study of Domain Effects in Underwater Object Detection

Melanie Wille, Dimity Miller, Tobias Fischer, Scarlett Raine

Keywords: underwater object detection, domain shift, domain generalization, data annotation, marine robotics

TL;DR: Our paper proposes an underwater domain-labeling framework based on interpretable environmental factors to systematically analyze how domain shift affects underwater object detection performance.

Abstract: Domain shift, where deviations between training and deployment data distributions degrade model performance, is a key challenge in underwater environments. Existing benchmarks testing performance for underwater domain shift simulate variability through synthetic style transfer. This fails to capture intrinsic scene factors such as visibility, illumination, scene composition, or acquisition factors, limiting analysis of real-world effects. We propose a labeling framework that defines underwater domains using measurable image, scene, and acquisition characteristics. Unlike prior benchmarks, it captures physically meaningful factors, enabling semantically consistent image grouping and supporting domain-specific evaluation of detection performance including failure analysis. We validate this on public datasets, showing systematic variations across domain factors and revealing hidden failure modes.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Paper Acceptance: No

Submission Number: 17